ObjectiveTo evaluate the effects of Tongnaoyin on the blood-brain barrier status and neurological impairment in acute ischemic stroke （AIS） patients with the syndrome of phlegm-stasis blocking collaterals by dynamic contrast-enhanced magnetic resonance imaging （DCE-MRI）. MethodsA total of 63 patients diagnosed with AIS in the Jiangsu Province Hospital of Chinese Medicine from October 2022 to December 2023 were enrolled in this study. According to random number table method，the patients were assigned into a control group （32 cases） and an observation group （31 cases）. The control group received conventional Western medical treatment，and the observation group took 200 mL Tongnaoyin after meals，twice a day from day 2 of admission on the basis of the treatment in the control group. After 7 days of treatment，the patients were examined by DCE-MRI. The baseline data for two groups of patients before treatment were compared. The National Institute of Health Stroke Scale （NIHSS） score and modified Rankin Scale （mRS） score were recorded before treatment and after 90 days of treatment for both groups. The rKtrans，rKep，and rVe values were obtained from the region of interest （ROI） of the infarct zone/mirror area and compared between the two groups. ResultsThere was no significant difference in the NIHSS or mRS score between the two groups before treatment. After 90 days of treatment，the NIHSS and mRS scores declined in both groups，and the observation group had lower scores than the control group （P<0.05）. After treatment，the rKtrans and rVe in the observation group were lower than those in the control group （P<0.01）. ConclusionCompared with conventional Western medical treatment alone，conventional Western medical treatment combined with Tongnaoyin accelerates the repair of the blood-brain barrier in AIS patients，thereby ameliorating neurological impairment after AIS to improve the prognosis.

OBJECTIVE: To investigate the predictive value of oxygenation index (PaO₂/FiO₂) at intensive care unit (ICU) admission on 30-day mortality in patients with sepsis. METHODS: A retrospective study was conducted. Patients with sepsis who were hospitalized in the ICU of the Affiliated Hospital of Jining Medical University from April 2015 to October 2023 were enrolled. The demographic information, comorbidities, sites of infection, vital signs and laboratory test indicators at the time of admission to the ICU, disease severity scores within 24 hours of admission to the ICU, treatment process and prognostic indicators were collected. According to the PaO₂/FiO₂ at ICU admission, patients were divided into Q1 group (PaO₂/FiO₂ of 4.1-16.4 cmHg, 1 cmHg ≈ 1.33 kPa), Q2 group (PaO₂/FiO₂ of 16.5-22.6 cmHg), Q3 group (PaO₂/FiO₂ of 22.7-32.9 cmHg), and Q4 group (PaO₂/FiO₂ of 33.0-94.8 cmHg). Differences in the indicators across the four groups were compared. Multifactorial Cox regression analysis was used to assess the relationship between PaO₂/FiO₂ and 30-day mortality of patients with sepsis. The predictive value of PaO₂/FiO₂, sequential organ failure assessment (SOFA) and acute physiology and chronic health evaluation II (APACHE II) on 30-day prognosis of patients with sepsis was analyzed by receiver operator characteristic curve (ROC curve). RESULTS: A total of 1 711 patients with sepsis were enrolled, including 428 patients in Q1 group, 424 patients in Q2 group, 425 patients in Q3 group, and 434 patients in Q4 group. 622 patients died at 30-day, the overall 30-day mortality was 36.35%. There were statistically significant differences in age, body mass index (BMI), history of smoking, history of alcohol consumption, admission heart rate, respiratory rate, APACHE II score, SOFA score, Glasgow coma score (GCS), site of infection, Combined chronic obstructive pulmonary disease (COPD), blood lactic acid (Lac), prothrombin time (PT), albumin (Alb), total bilirubin (TBil), pH, proportion of mechanical ventilation, duration of mechanical ventilation, proportion of vasoactive medication used, and maximal concentration, length of ICU stay, hospital stay, incidence of acute kidney injury, in-hospital mortality, 30-day mortality among the four groups. Multivariate Cox regression analysis showed that after adjusting for confounding factors, for every 1 cmHg increase in PaO₂/FiO₂ at ICU admission, the 30-day mortality risk decreased by 2% [hazard ratio (HR) = 0.98, 95% confidence interval (95%CI) was 0.98-0.99, P < 0.001]. The 30-day mortality risk in the Q4 group was reduced compared with the Q1 group by 41% (HR = 0.59, 95%CI was 0.46-0.76, P < 0.001). The fitted curve showed that a curvilinear relationship between PaO₂/FiO₂ and 30-day mortality after adjustment for confounders. In the inflection point analysis, for every 1 cmHg increase in PaO₂/FiO₂ at PaO₂/FiO₂ < 28.55 cmHg, the risk of 30-day death in sepsis patients was reduced by 5% (HR = 0.95, 95%CI was 0.94-0.97, P < 0.001); when PaO₂/FiO₂ ≥ 28.55 cmHg, there was no statistically significant association between PaO2/FiO2 and the increase in the risk of 30-day death in sepsis (HR = 1.01, 95%CI was 0.99-1.02, P = 0.512). ROC curve analysis showed that the area under the curve (AUC) for the prediction of 30-day mortality by admission PaO₂/FiO₂ in ICU sepsis patients was 0.650, which was lower than the predictive ability of the SOFA score (AUC = 0.698) and APACHE II score (AUC = 0.723). CONCLUSION In patients with sepsis, PaO₂/FiO₂ at ICU admission is strongly associated with 30-day mortality risk, alerting healthcare professionals to pay attention to patients with low PaO₂/FiO₂ for timely interventions.
Humans ; Sepsis/mortality* ; Intensive Care Units ; Retrospective Studies ; Prognosis ; Hospital Mortality ; Oxygen ; Male ; Predictive Value of Tests ; Female ; Middle Aged ; Aged

Objective: To investigate the efficacy, nursing characteristics, and management of different desensitization strategies before allogeneic hematopoietic stem cell transplantation (allo-HSCT) among patients with high level of human leukocyte antigen (HLA) antibodies. Methods: A retrospective analysis was conducted on 82 patients with high levels of HLA antibodies who underwent allo-HSCT at the First Affiliated Hospital of Soochow University and Suzhou Hopes Hematonosis Hospital between January 2020 to November 2023. Patients were divided into two groups based on the desensitization strategy they received: the anti-CD20 monoclonal antibody combined with therapeutic plasma exchange (TPE) group (n=50) and the anti-CD20 monoclonal antibody combined with Protein A immunoabsorption group (n=32). The differences of efficacy between the desensitization strategies were analyzed. The safety of both desensitization strategies were assessed by close monitoring of adverse events throughout the treatment. The nursing characteristics and interventions specific to these strategies were comprehensively summarized. Results: There were no significant differences in age, gender, and diagnosis between the two groups of patients receiving different desensitization strategies (P>0.05). Following desensitization in the immunoadsorption group, the mean fluorescence intensity (MFI) levels of anti-HLA Class I antibody decreased significantly compared to initial screening (P=0.048), while the decrease in MFI values of anti-HLA Class II antibody was not statistically significant (P=0.173). In the TPE group, the MFI levels for both anti-HLA Class I and II antibodies after desensitization decreased significantly compared to initial screening (P=0.025 and 0.028, respectively). Monitoring of adverse events during desensitization treatment, found that patients in the immunoadsorption group experienced mild decreases in blood pressure during the process, with two patients developing severe hypotension. No allergic reactions occurred, and no damage of liver or kidney function was observed after the immunoadsorption. In the immunoadsorption group, a total of 19 patients underwent sera immunoglobulin assays before and after immunoadsorption. Compared to the initial screening, the immunoglobulin G (IgG) levels significantly decreased after immunoadsorption (P<0.001). In TPE group, 12 patients experienced mild hypotension during the plasma exchange process, but no severe hypotension was observed. One patient developed an allergic reaction. After the TPE treatment, no damage of liver or kidney function was observed, nor any decrease of IgG levels. In terms of safety of intravenous access, neither group experienced severe complications such as catheter-related bloodstream infections or deep vein thrombosis. In the TPE group, catheter occlusion occurred during the process of plasma exchange in 2 patients, while no such incident was observed in the immunoadsorption group. Patients of both groups exhibited anxiety and depression before treatment. After psychological care, the scores for anxiety and depression significantly decreased (P<0.001). Conclusion: Both desensitization strategies significantly decreased the HLA antibodies in highly sensitized patients with high level of HLA antibodies undergoing allo-HSCT. For patients receiving immunoabsorption, nursing care should focus on preventing and managing hypotension and implementing infection-prevention measures due to IgG depletion. In contrast, for those undergoing TPE, vigilant monitoring and prompt management of potential allergic reactions are essential components of nursing practice.

Objective:To describe the epidemiological characteristics of respiratory syncytial virus (RSV) infection in preschool children and explore the risk factors for severe pneumonia.Methods:Epidemiological data of 279 preschool children with RSV infection were investigated. The children were screened for severe pneumonia and separated into ordinary and severe types. General data and laboratory test data from both groups were compared, and binary logistic regression model analysis was applied to determine the risk factors for severe pneumonia.Results:Preschool children with RSV infection were mostly male (63.08%), <6 months old (65.95%) and had poor living environment (53.05%), with main symptoms of cough (91.04%) and wheezing (69.18%), the lung auscultation was mainly characterized by wheezing (86.74%), and imaging findings were mainly patchy shadows (76.34%), the onset season was concentrated in autumn (31.18%) and winter (43.37%). The detection rate of severe pneumonia in 279 pediatric patients was 20.27% (56/279). The proportions of onset season being autumn or winter, low birth weight infants, history of respiratory infections within 3 months, delayed treatment, neutrophils count <10×10 9/L, C-reactive protein≥10 mg/L, procalcitonin≥1.5 ng/mL, albumin<30 g/L, CD4 + /CD8 + <1.2 in the severe types were higher than those in the normal types ( P<0.05). Logistic regression analysis showed that the onset season was autumn or winter ( OR=2.316, 95% CI: 1.235-4.345), low birth weight infants ( OR=2.679, 95% CI: 1.442-4.977), history of respiratory infections within 3 months ( OR=2.815, 95% CI: 1.539-5.148), delayed treatment ( OR=2.869, 95% CI: 1.581-5.206), low albumin<30 g/L ( OR=2.756, 95% CI: 1.495-5.080), and low CD4 + /CD8 + <1.2 ( OR=3.016, 95% CI: 1.695-5.366) were risk factors for severe RSV pneumonia in preschool children ( P<0.05). Conclusions:Autumn and winter, low birth weight infants, history of respiratory infections within 3 months, delayed treatment, low albumin, and low CD4 + /CD8 + are related to the occurrence of severe RSV pneumonia in preschool children. Therefore, it is necessary to strengthen the attention to the condition of preschool RSV infected children with the above risk factors, and actively intervene in controllable factors to reduce the risk of severe pneumonia.

Objective:To investigate the value of nomogram based on radiomics features of CT enterography (CTE) combined with clinical characteristics to predict secondary loss of response (SLOR) after infliximab (IFX) treatment in patients with Crohn′s disease (CD).Methods:This study was a case-control study. Clinical and imaging data of 155 patients with CD diagnosed at the First Affiliated Hospital of Anhui Medical University from March 2015 to July 2022 were retrospectively collected. The patients were divided into a training set ( n=108) and a testing set ( n=47) in the ratio of 7∶3 by stratified sampling method. All patients were treated according to the standardized protocol and were classified as SLOR (43 in the training set and 18 in the testing set) and non-SLOR (65 in the training set and 29 in the testing set) according to treatment outcome. Based on the data from the training group, independent clinical predictors of SLOR after IFX treatment were screened in the clinical data using univariate and multivariate logistic regression analysis to establish a clinical model. Intestinal phase images were selected to be outlined layer by layer along the margin of the lesion to obtain the volume of the region of interest to extract the radiomics features. The radiomics features were screened using univariate analysis and the minimum absolute shrinkage and selection operator to establish the radiomics model. Multivariate logistic regression analysis was used to build a combined clinical-radiomics model based on the screened clinical independent predictors and radiomics characters, then a nomogram was drawn. The predictive efficacy of the 3 models for SLOR after IFX treatment was assessed by receiver operating characteristic curves, and the area under the curve (AUC) was calculated. The decision curve analysis was applied to evaluate the clinical utility of the models. Results:Disease duration ( OR=1.983, 95% CI 1.966-2.000, P=0.046) and intestinal stenosis ( OR=1.246, 95% CI 1.079-1.764, P=0.015) were identified as the independent predictors of SLOR in the clinical data, and a clinical model was established. Totally 9 radiomics features were included in the radiomics model. The AUCs of clinical, radiomics, and combined models for predicting SLOR after IFX treatment in CD patients were 0.691 (95% CI 0.591-0.792), 0.896 (95% CI 0.836-0.955), and 0.910 (95% CI 0.855-0.965) in the training set, and 0.722 (95% CI 0.574-0.871), 0.866 (95% CI 0.764-0.968), and 0.889 (95% CI 0.796-0.982) in the testing set. Decision curve analysis in the testing set showed higher net clinical benefits for both the radiomics model and combined model than the clinical model, and combined model had higher net clinical benefits than the radiomics model over most threshold probability intervals. Conclusions:CTE-based radiomics model can effectively predict SLOR after IFX treatment in patients with CD, and a combined model by incorporating clinical characteristics of disease duration and intestinal stenosis can further improve the predictive efficacy.

ObjectiveTo investigate the changes in cerebral blood perfusion in patients with acute cerebral infarction after taking Tongnaoyin， a traditional Chinese medicine， based on head and neck computed tomography （CT） angiography （CTA） combined with brain CT perfusion imaging （CTP）. MethodA total of 240 patients with cerebral infarction of phlegm and blood stasis syndrome treated in Jiangsu Province Hospital of Traditional Chinese Medicine from March 2018 to September 2023 were randomly divided into a control group （99 cases） and a Tongnaoyin group （141 cases）. Based on the guidelines， the control group was treated with conventional treatment such as anti-aggregation， anticoagulation， lipid-lowering and plaque stabilization， brain protection， and supportive treatment. The Tongnaoyin group was treated with Tongnaoyin of 200 mL in warm conditions in the morning and evening on the basis of the control group. Both groups underwent CTA combined with CTP within 24 hours after admission， and they were reexamined by CTA and CTP in the sixth month after admission. The degree of intracranial artery stenosis was determined according to the North American Symptomatic Carotid Endarterectomy Trial （NASCET） method. The relative cerebral blood volume （rCBV）， relative cerebral blood flow （rCBF）， mean transit time （MTT）， and time to peak （TTP） of the lesion area before and after treatment were compared. The adverse outcomes of the two groups within six months after discharge were compared. ResultCompared with the group before treatment， the degree of vascular stenosis in the Tongnaoyin group was significantly reduced， and the difference was statistically significant （Z=105.369，P<0.05）. Compared with the control group after treatment， the improvement rate of vascular stenosis in the Tongnaoyin group was higher （χ²=84.179，P<0.01）， and the curative effect was better.After treatment， the rCBV and rCBF of patients in the Tongnaoyin group were significantly increased， and the difference was statistically significant （P<0.01）. MTT and TTP showed a trend of shortening， but the difference was not statistically significant. There was no statistically significant difference in rCBV， rCBF， MTT， and TTP in the control group. Compared with those in the control group after treatment， the rCBV and rCBF in the Tongnaoyin group were significantly increased， while MTT and TTP were significantly reduced （P<0.01）. After six months of discharge， the risk of poor prognosis in the Tongnaoyin group was significantly reduced compared with the control group （P<0.05）. ConclusionTongnaoyin has a good effect on improving cerebral blood perfusion in patients with acute cerebral infarction. It can be used as an effective supplement for the conventional treatment of ischemic stroke to improve clinical efficacy.

Objective:To explore the current situation and influencing factors of quality of life of septic patients in intensive care unit (ICU) after discharge, and to provide theoretical basis for clinical early psychological intervention and continuity of care.Methods:A prospective observational study was conducted. The septic patients who were hospitalized in the department of critical care medicine of the Affiliated Hospital of Jining Medical University and discharged with improvement from January 1 to December 31, 2022 were selected as the research objects. The demographic information, basic diseases, infection site, vital signs at ICU admission, severity scores of the condition within 24 hours after ICU admission, various biochemical indexes, treatment process, and prognostic indexes of all the patients were recorded. All patients were assessed by questionnaire at 3 months of discharge using the 36-item short-form health survey scale (SF-36 scale), the activities of daily living scale (ADL scale), and the Montreal cognitive assessment scale (MoCA scale). Multiple linear regression was used to analyze the factors influencing the quality of life of septic patients after discharge from the hospital.Results:A total of 200 septic patients were discharged with improvement and followed up at 3 months of discharge, of which 150 completed the questionnaire. Of the 150 patients, 57 had sepsis and 93 had septic shock. The total SF-36 scale score of septic patients at 3 months of discharge was 81.4±23.0, and the scores of dimensions were, in descending order, role-emotional (83.4±23.0), mental health (82.9±23.6), bodily pain (82.8±23.3), vitality (81.6±23.2), physical function (81.4±23.5), general health (81.1±23.3), role-physical (79.5±27.0), and social function (78.8±25.2). There was no statistically significant difference in the total SF-36 scale score between the patients with sepsis and septic shock (82.6±22.0 vs. 80.7±23.6, P > 0.05). Incorporating the statistically significant indicators from linear univariate analysis into multiple linear regression analysis, and the results showed that the factors influencing the quality of life of septic patients at 3 months after discharge included ADL scale score at 3 months after discharge [ β= 0.741, 95% confidence interval (95% CI) was 0.606 to 0.791, P < 0.001], length of ICU stay ( β= -0.209, 95% CI was -0.733 to -0.208, P = 0.001), duration of mechanical ventilation ( β= 0.147, 95% CI was 0.122 to 0.978, P = 0.012), total dosage of norepinephrine ( β= -0.111, 95% CI was -0.044 to -0.002, P = 0.028), mean arterial pressure (MAP) at ICU admission ( β= -0.102, 95% CI was -0.203 to -0.007, P = 0.036) and body weight ( β= 0.097, 95% CI was 0.005 to 0.345, P = 0.044). Conclusions:The quality of life of patients with sepsis at 3 months after discharge is at a moderately high level. The influencing factors of the quality of life of patients with sepsis at 3 months after discharge include the ADL scale score at 3 months after discharge, the length of ICU stay, the duration of mechanical ventilation, the total dosage of norepinephrine, MAP at ICU admission and body weight, and healthcare professionals should enhance the treatment and care of the patients during their hospitalization based on the above influencing factors, and pay attention to early psychological intervention and continued care for such patients.

Objective:To construct a nomogram model predicting the occurrence of acute kidney injury (AKI) in patients with sepsis in the intensive care unit (ICU), and to verify its validity for early prediction.Methods:Sepsis patients admitted to the ICU of the Affiliated Hospital of Jining Medical University from April 2015 to December 2021 were retrospectively included, and those who met the inclusion criteria were randomly divided into training and validation sets at a ratio of 7:3. Univariate and multivariate logistic regression models were used to identify independent risk factors for AKI in patients with sepsis, and a nomogram was constructed based on the independent risk factors. Calibration curve, receiver operating characteristic (ROC) curve, and decision curve analysis (DCA) were used to evaluate the nomogram model.Results:741 patients with sepsis were included in the study, 335 patients developed AKI within 7 d of ICU admission, with an AKI incidence of 45.1%. Randomization was performed in the training set ( n=519) and internal validation set ( n=222). Multivariate logistic analysis revealed that acute physiology and chronic health status score Ⅱ, sequential organ failure score, serum lactate, calcitoninogen, norepinephrine dose, urea nitrogen, and neutrophil percentage were independent factors influencing the occurrence of AKI, and a nomogram model was constructed by combining these variables. In the training set, the AUC of the nomogram model ROC was 0.875 (95% CI: 0.767-0.835), the calibration curve showed consistency between the predicted and actual probabilities, and the DCA showed a good net clinical benefit. In the internal validation set, the nomogram model had a similar predictive value for AKI (AUC=0.871, 95% CI: 0.734-0.854). Conclusions:A nomogram model constructed based on the critical care score at admission combined with inflammatory markers can be used for the early prediction of AKI in sepsis patients in the ICU. The model is helpful for clinicians early identify AKI in sepsis patients.

Objective:To explore the effects of online supportive disclosure therapy on the self-expression level, professional identity, dimission intention, and turnover rate of pre-dimission nurses, in order to provide a reference for nursing managers to stabilize the nursing team.Methods:A quasi experimental research method was used, and a convenient sampling method was used to select 192 pre resigned nurses from Shandong Provincial Third Hospital, the First Affiliated Hospital of Shandong First Medical University, and Shandong First Medical University Affiliated Provincial Hospital from October 2021 to December 2022 as the research subjects. They were divided into a control group and an experimental group by random number table method, with 96 nurses in each group. The control group received routine exit interviews, while the experimental group received online supportive disclosure therapy intervention based on this. The self-expression level, professional identity, dimission intention, and turnover rate of two groups of nurses before and 1, 2 months after the intervention were evaluated.Results:Finally, 94 nurses in the control group and 92 nurses in the experimental group completed the study. There were no significant differences in the self-expression level, professional identity, dimission intention before the intervention between the two groups ( P>0.05). After 1 and 2 months of the intervention, the scores of the Pain Self Disclosure Index, Nurse Professional Identity Rating Scale, and Resignation Intention Scale of the experimental group were 36.33 ± 5.13, 73.88 ± 8.72, 14.18 ± 1.12 and 34.22 ± 6.78, 98.26 ± 11.29, 6.16 ± 1.19, respectively,and the control group were 28.06 ± 8.23, 64.72 ± 10.39, 17.82 ± 1.37 and 44.26 ± 7.62, 79.82 ± 8.66, 9.18 ± 1.06, there were statistically significant differences between the two groups ( t values were -13.54 to -2.11, all P<0.05); there were statistically significant differences in the inter group effects, time effects, and interaction effects of the scores on the Pain Self Disclosure Index, Professional Identity Rating Scale, and Resignation Intention Scale between the two groups ( F values were 5.12 to 14.82, all P<0.05). The turnover rate of nurses in the experimental group was 1.09% (1/92), lower than 8.51% (8/94) in the control group, and the difference between the two groups was statistically significant ( χ2=1.59, P<0.05). Conclusions:Online supportive disclosure therapy can improve the self-expression level and professional identity of pre-dimission nurses, and reduce their willingness to resign and turnover rate.

OBJECTIVE: To analyze the risk factors of in-hospital death in patients with sepsis in the intensive care unit (ICU) based on machine learning, and to construct a predictive model, and to explore the predictive value of the predictive model. METHODS: The clinical data of patients with sepsis who were hospitalized in the ICU of the Affiliated Hospital of Jining Medical University from April 2015 to April 2021 were retrospectively analyzed,including demographic information, vital signs, complications, laboratory examination indicators, diagnosis, treatment, etc. Patients were divided into death group and survival group according to whether in-hospital death occurred. The cases in the dataset (70%) were randomly selected as the training set for building the model, and the remaining 30% of the cases were used as the validation set. Based on seven machine learning models including logistic regression (LR), K-nearest neighbor (KNN), support vector machine (SVM), decision tree (DT), random forest (RF), extreme gradient boosting (XGBoost) and artificial neural network (ANN), a prediction model for in-hospital mortality of sepsis patients was constructed. The receiver operator characteristic curve (ROC curve), calibration curve and decision curve analysis (DCA) were used to evaluate the predictive performance of the seven models from the aspects of identification, calibration and clinical application, respectively. In addition, the predictive model based on machine learning was compared with the sequential organ failure assessment (SOFA) and acute physiology and chronic health evaluation II (APACHE II) models. RESULTS: A total of 741 patients with sepsis were included, of which 390 were discharged after improvement, 351 died in hospital, and the in-hospital mortality was 47.4%. There were significant differences in gender, age, APACHE II score, SOFA score, Glasgow coma score (GCS), heart rate, oxygen index (PaO₂/FiO₂), mechanical ventilation ratio, mechanical ventilation time, proportion of norepinephrine (NE) used, maximum NE, lactic acid (Lac), activated partial thromboplastin time (APTT), albumin (ALB), serum creatinine (SCr), blood urea nitrogen (BUN), blood uric acid (BUA), pH value, base excess (BE), and K⁺ between the death group and the survival group. ROC curve analysis showed that the area under the curve (AUC) of RF, XGBoost, LR, ANN, DT, SVM, KNN models, SOFA score, and APACHE II score for predicting in-hospital mortality of sepsis patients were 0.871, 0.846, 0.751, 0.747, 0.677, 0.657, 0.555, 0.749 and 0.760, respectively. Among all the models, the RF model had the highest precision (0.750), accuracy (0.785), recall (0.773), and F1 score (0.761), and best discrimination. The calibration curve showed that the RF model performed best among the seven machine learning models. DCA curve showed that the RF model exhibited greater net benefit as well as threshold probability compared to other models, indicating that the RF model was the best model with good clinical utility. CONCLUSIONS The machine learning model can be used as a reliable tool for predicting in-hospital mortality in sepsis patients. RF models has the best predictive performance, which is helpful for clinicians to identify high-risk patients and implement early intervention to reduce mortality.
Humans ; Hospital Mortality ; Retrospective Studies ; ROC Curve ; Prognosis ; Sepsis/diagnosis* ; Intensive Care Units